commit 7019fff19756133e57d51ec1e6f7e4537b331d66 Author: ModelHub XC Date: Thu Jun 25 13:30:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/qwen2.5-3b-or1-tensopolis-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cdb2005 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +qwen2.5-3b-or1-tensopolis.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-3b-or1-tensopolis.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-3b-or1-tensopolis.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-3b-or1-tensopolis.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-3b-or1-tensopolis.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-3b-or1-tensopolis.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-3b-or1-tensopolis.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-3b-or1-tensopolis.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-3b-or1-tensopolis.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-3b-or1-tensopolis.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-3b-or1-tensopolis.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-3b-or1-tensopolis.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d2cbf00 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: tensopolis/qwen2.5-3b-or1-tensopolis +datasets: +- open-r1/OpenR1-Math-220k +language: +- en +library_name: transformers +license_link: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE +license_name: qwen-research +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2.5 +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/tensopolis/qwen2.5-3b-or1-tensopolis + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#qwen2.5-3b-or1-tensopolis-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-3b-or1-tensopolis-GGUF/resolve/main/qwen2.5-3b-or1-tensopolis.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-3b-or1-tensopolis-GGUF/resolve/main/qwen2.5-3b-or1-tensopolis.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-3b-or1-tensopolis-GGUF/resolve/main/qwen2.5-3b-or1-tensopolis.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-3b-or1-tensopolis-GGUF/resolve/main/qwen2.5-3b-or1-tensopolis.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-3b-or1-tensopolis-GGUF/resolve/main/qwen2.5-3b-or1-tensopolis.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-3b-or1-tensopolis-GGUF/resolve/main/qwen2.5-3b-or1-tensopolis.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-3b-or1-tensopolis-GGUF/resolve/main/qwen2.5-3b-or1-tensopolis.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-3b-or1-tensopolis-GGUF/resolve/main/qwen2.5-3b-or1-tensopolis.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-3b-or1-tensopolis-GGUF/resolve/main/qwen2.5-3b-or1-tensopolis.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-3b-or1-tensopolis-GGUF/resolve/main/qwen2.5-3b-or1-tensopolis.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-3b-or1-tensopolis-GGUF/resolve/main/qwen2.5-3b-or1-tensopolis.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-3b-or1-tensopolis-GGUF/resolve/main/qwen2.5-3b-or1-tensopolis.f16.gguf) | f16 | 6.3 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + + diff --git a/qwen2.5-3b-or1-tensopolis.IQ4_XS.gguf b/qwen2.5-3b-or1-tensopolis.IQ4_XS.gguf new file mode 100644 index 0000000..246cca6 --- /dev/null +++ b/qwen2.5-3b-or1-tensopolis.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b332712b42452691e2ee81d5543748d86ca6d20a8c23ff079a9b0a9109388f96 +size 1753184256 diff --git a/qwen2.5-3b-or1-tensopolis.Q2_K.gguf b/qwen2.5-3b-or1-tensopolis.Q2_K.gguf new file mode 100644 index 0000000..0de3a85 --- /dev/null +++ b/qwen2.5-3b-or1-tensopolis.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d7cf2608673d9da3fd68476edd4aad2fa55f831d6cec3e3b792fd0a039e7603 +size 1274755072 diff --git a/qwen2.5-3b-or1-tensopolis.Q3_K_L.gguf b/qwen2.5-3b-or1-tensopolis.Q3_K_L.gguf new file mode 100644 index 0000000..9bb3544 --- /dev/null +++ b/qwen2.5-3b-or1-tensopolis.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0738f905c93a9ea8a7756cfd84c6a5a4daf9e27209f51d68904a992ace48d1e2 +size 1707390976 diff --git a/qwen2.5-3b-or1-tensopolis.Q3_K_M.gguf b/qwen2.5-3b-or1-tensopolis.Q3_K_M.gguf new file mode 100644 index 0000000..8b923a0 --- /dev/null +++ b/qwen2.5-3b-or1-tensopolis.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eb8c026619a905f79b8b279f9508497c47719ad98004088a1b277229c7875ce +size 1590474752 diff --git a/qwen2.5-3b-or1-tensopolis.Q3_K_S.gguf b/qwen2.5-3b-or1-tensopolis.Q3_K_S.gguf new file mode 100644 index 0000000..e6d4b47 --- /dev/null +++ b/qwen2.5-3b-or1-tensopolis.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58b5bb864797390c8f60018c103005f6e8af0170d7e65bc60b96a53fba65bdfe +size 1454356480 diff --git a/qwen2.5-3b-or1-tensopolis.Q4_K_M.gguf b/qwen2.5-3b-or1-tensopolis.Q4_K_M.gguf new file mode 100644 index 0000000..f8cd386 --- /dev/null +++ b/qwen2.5-3b-or1-tensopolis.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5d2a8135e5f8f8b57cf32d71ad07d288447a6de2f079693a504332a44935de3 +size 1929902080 diff --git a/qwen2.5-3b-or1-tensopolis.Q4_K_S.gguf b/qwen2.5-3b-or1-tensopolis.Q4_K_S.gguf new file mode 100644 index 0000000..846f4b6 --- /dev/null +++ b/qwen2.5-3b-or1-tensopolis.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddafcef3e57fcc0839bbdadbf6e20ae702ccf66bcdc910e12527ac57d79abd20 +size 1834383360 diff --git a/qwen2.5-3b-or1-tensopolis.Q5_K_M.gguf b/qwen2.5-3b-or1-tensopolis.Q5_K_M.gguf new file mode 100644 index 0000000..e0d78e0 --- /dev/null +++ b/qwen2.5-3b-or1-tensopolis.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:552098555c5971705d63d6c7e59b4717ab2b707008c6f8827a775811d7536d86 +size 2224814080 diff --git a/qwen2.5-3b-or1-tensopolis.Q5_K_S.gguf b/qwen2.5-3b-or1-tensopolis.Q5_K_S.gguf new file mode 100644 index 0000000..71a1753 --- /dev/null +++ b/qwen2.5-3b-or1-tensopolis.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf36a532faf75fcf9f16eb938aa2870f1d7790134b9eac2829fc4fe39359da0b +size 2169665536 diff --git a/qwen2.5-3b-or1-tensopolis.Q6_K.gguf b/qwen2.5-3b-or1-tensopolis.Q6_K.gguf new file mode 100644 index 0000000..1b77b8c --- /dev/null +++ b/qwen2.5-3b-or1-tensopolis.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2935d3e32b372bf0f404bff1eb90bc1a05ad35377b6eff4c6601630f71bfa351 +size 2538158080 diff --git a/qwen2.5-3b-or1-tensopolis.Q8_0.gguf b/qwen2.5-3b-or1-tensopolis.Q8_0.gguf new file mode 100644 index 0000000..71c528e --- /dev/null +++ b/qwen2.5-3b-or1-tensopolis.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e2c887c32c61eaf327e89602ebef6b270743301917be05646a70fd8a921ce2a +size 3285475328 diff --git a/qwen2.5-3b-or1-tensopolis.f16.gguf b/qwen2.5-3b-or1-tensopolis.f16.gguf new file mode 100644 index 0000000..f9ec42f --- /dev/null +++ b/qwen2.5-3b-or1-tensopolis.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:662d1f5ef39c672c94ff33b3338763b1fe3b139feb9d8e7cb59fb58a50d12a3f +size 6178316288